Browse Source

Merge branch 'pr-amery-textparser' into next-amery

dev-amery-decoder
Alejandro Mery 1 year ago
parent
commit
7e2797607d
  1. 5
      go.mod
  2. 10
      go.sum
  3. 63
      parser/lexer.go
  4. 43
      parser/parser.go
  5. 102
      parser/text.go

5
go.mod

@ -10,16 +10,17 @@ require (
require (
github.com/BurntSushi/toml v1.3.2 // indirect
github.com/chavacava/garif v0.0.0-20230608123814-4bd63c2919ab // indirect
github.com/chavacava/garif v0.1.0 // indirect
github.com/fatih/color v1.15.0 // indirect
github.com/fatih/structtag v1.2.0 // indirect
github.com/mattn/go-colorable v0.1.13 // indirect
github.com/mattn/go-isatty v0.0.19 // indirect
github.com/mattn/go-runewidth v0.0.9 // indirect
github.com/mattn/go-runewidth v0.0.15 // indirect
github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517 // indirect
github.com/mitchellh/go-homedir v1.1.0 // indirect
github.com/olekukonko/tablewriter v0.0.5 // indirect
github.com/pkg/errors v0.9.1 // indirect
github.com/rivo/uniseg v0.4.4 // indirect
golang.org/x/mod v0.12.0 // indirect
golang.org/x/sys v0.11.0 // indirect
)

10
go.sum

@ -2,8 +2,8 @@ asciigoat.org/core v0.3.7 h1:tMasdvZgsMJJMVsZVfXXB5lqq82pFiCsyEmOEmcmAfI=
asciigoat.org/core v0.3.7/go.mod h1:tXj+JUutxRbcO40ZQRuUVaZ4rnYz1kAZ0nblisV8u74=
github.com/BurntSushi/toml v1.3.2 h1:o7IhLm0Msx3BaB+n3Ag7L8EVlByGnpq14C4YWiu/gL8=
github.com/BurntSushi/toml v1.3.2/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
github.com/chavacava/garif v0.0.0-20230608123814-4bd63c2919ab h1:5JxePczlyGAtj6R1MUEFZ/UFud6FfsOejq7xLC2ZIb0=
github.com/chavacava/garif v0.0.0-20230608123814-4bd63c2919ab/go.mod h1:XMyYCkEL58DF0oyW4qDjjnPWONs2HBqYKI+UIPD+Gww=
github.com/chavacava/garif v0.1.0 h1:2JHa3hbYf5D9dsgseMKAmc/MZ109otzgNFk5s87H9Pc=
github.com/chavacava/garif v0.1.0/go.mod h1:XMyYCkEL58DF0oyW4qDjjnPWONs2HBqYKI+UIPD+Gww=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@ -16,8 +16,9 @@ github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovk
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/mattn/go-runewidth v0.0.9 h1:Lm995f3rfxdpd6TSmuVCHVb/QhupuXlYr8sCI/QdE+0=
github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
github.com/mattn/go-runewidth v0.0.15 h1:UNAjwbU9l54TA3KzvqLGxwWjHmMgBUVhBiTjelZgg3U=
github.com/mattn/go-runewidth v0.0.15/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517 h1:zpIH83+oKzcpryru8ceC6BxnoG8TBrhgAvRg8obzup0=
github.com/mgechev/dots v0.0.0-20210922191527-e955255bf517/go.mod h1:KQ7+USdGKfpPjXk4Ga+5XxQM4Lm4e3gAogrreFAYpOg=
github.com/mgechev/revive v1.3.3 h1:GUWzV3g185agbHN4ZdaQvR6zrLVYTUSA2ktvIinivK0=
@ -30,6 +31,9 @@ github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
github.com/rivo/uniseg v0.4.4 h1:8TfxU8dW6PdqD27gjM8MVNuicgxIjxpm4K7x4jp8sis=
github.com/rivo/uniseg v0.4.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=

63
parser/lexer.go

@ -5,71 +5,42 @@ import "asciigoat.org/core/lexer"
// Run parses the source
func (p *Parser) Run() error {
p.setDefaults()
p.pos.Reset()
return lexer.Run(p.lexStart)
}
func (p *Parser) lexStart() (lexer.StateFn, error) {
for {
r, _, err := p.src.ReadRune()
r, _, err := p.p.ReadRune()
switch {
case err != nil:
return p.emitError("", err)
case IsNewLine(r):
// new line
p.lexMoreNewLine(r)
p.p.UnreadRune()
p.p.AcceptNewLine()
p.stepLine()
case IsSpace(r):
// whitespace
p.stepRune()
p.stepString()
case IsCommentStart(r):
// switch to comment lexer
p.src.UnreadRune()
p.p.UnreadRune()
return p.lexComment, nil
case IsSectionStart(r):
// section
return p.lexSectionStart, nil
default:
// entry
p.src.UnreadRune()
p.p.UnreadRune()
return p.lexEntryStart, nil
}
}
}
func (p *Parser) lexMoreNewLine(r1 rune) {
// r1 is warrantied to be either '\r' or '\n'
r2, _, err := p.src.ReadRune()
switch r1 {
case '\n':
switch {
case r2 == '\r':
// LN CR
case err == nil:
// LN
p.src.UnreadRune()
default:
// LN EOF
}
case '\r':
switch {
case r2 == '\n':
// CR LN
case err == nil:
// CR
p.src.UnreadRune()
default:
// CR EOF
}
default:
panic("unreachable")
}
}
func (p *Parser) lexComment() (lexer.StateFn, error) {
// until the end of the line
p.src.AcceptAll(IsNotNewLine)
p.p.AcceptAll(IsNotNewLine)
err := p.emitString(TokenComment)
return p.lexStart, err
@ -81,11 +52,11 @@ func (p *Parser) lexSectionStart() (lexer.StateFn, error) {
}
// remove whitespace between `[` and the name
if p.src.AcceptAll(IsSpaceNotNewLine) {
if p.p.AcceptAll(IsSpaceNotNewLine) {
p.stepString()
}
if !p.src.AcceptAll(IsName) {
if !p.p.AcceptAll(IsName) {
// no name
return p.emitError("section name missing", lexer.ErrUnacceptableRune)
}
@ -94,12 +65,12 @@ func (p *Parser) lexSectionStart() (lexer.StateFn, error) {
return nil, err
}
// remove whitespace between the name andthe closing `]`
if p.src.AcceptAll(IsSpaceNotNewLine) {
// remove whitespace between the name and the closing `]`
if p.p.AcceptAll(IsSpaceNotNewLine) {
p.stepString()
}
r, _, err := p.src.ReadRune()
r, _, err := p.p.ReadRune()
switch {
case err != nil:
return p.emitError("", err)
@ -112,17 +83,17 @@ func (p *Parser) lexSectionStart() (lexer.StateFn, error) {
}
func (p *Parser) lexEntryStart() (lexer.StateFn, error) {
p.src.AcceptAll(IsName)
p.p.AcceptAll(IsName)
if err := p.emitString(TokenFieldKey); err != nil {
return nil, err
}
// ignore whitespace between key and the '=' sign
if p.src.AcceptAll(IsSpaceNotNewLine) {
if p.p.AcceptAll(IsSpaceNotNewLine) {
p.stepString()
}
r, _, err := p.src.ReadRune()
r, _, err := p.p.ReadRune()
switch {
case err != nil:
return p.emitError("", err)
@ -131,11 +102,11 @@ func (p *Parser) lexEntryStart() (lexer.StateFn, error) {
}
// ignore whitespace between the '=' and the value
if p.src.AcceptAll(IsSpaceNotNewLine) {
if p.p.AcceptAll(IsSpaceNotNewLine) {
p.stepString()
}
p.src.AcceptAll(IsNotNewLine)
p.p.AcceptAll(IsNotNewLine)
if err := p.emitString(TokenFieldValue); err != nil {
return nil, err
}

43
parser/parser.go

@ -1,4 +1,4 @@
// Package parser parses dosini-style files
// Package parser parses ini-style files
package parser
import (
@ -8,10 +8,9 @@ import (
"asciigoat.org/core/lexer"
)
// Parser parses a dosini-style document
// Parser parses a ini-style document
type Parser struct {
src *lexer.Reader
pos lexer.Position
p TextParser
// OnToken is called for each identified token. if it returns an error
// parsing is interrupted.
@ -51,15 +50,13 @@ func (p *Parser) setDefaults() {
}
func (p *Parser) emitString(typ TokenType) error {
s := p.src.Emit()
err := p.OnToken(p.pos, typ, s)
p.pos.StepN(len(s))
return err
pos, s := p.p.Emit()
return p.OnToken(pos, typ, s)
}
func (p *Parser) emitError(content string, err error) (lexer.StateFn, error) {
err2 := p.OnError(p.pos, content, err)
pos := p.p.Position()
err2 := p.OnError(pos, content, err)
switch {
case err2 != nil:
// return wrapped error
@ -77,33 +74,25 @@ func (p *Parser) emitInvalidRune(r rune) (lexer.StateFn, error) {
// stepLine discards the data and moves the position
// to the next line.
func (p *Parser) stepLine() {
p.src.Discard()
p.pos.StepLine()
}
// stepRune discards the data and moves the position
// one rune forward on the same line.
func (p *Parser) stepRune() {
p.src.Discard()
p.pos.Step()
p.p.StepLine()
}
// stepString discards the data and moves the position
// forward on the same line the length of the discarded
// content.
func (p *Parser) stepString() {
s := p.src.Emit()
p.pos.StepN(len(s))
p.p.Step()
}
// NewParser creates a dosini-style parser using
// NewParser creates a ini-style parser using
// an [io.Reader] as source
func NewParser(r io.Reader) *Parser {
if r == nil {
return nil
}
var p *Parser
return &Parser{
src: lexer.NewReader(r),
if r != nil {
p = new(Parser)
p.p.Init(r)
}
return p
}

102
parser/text.go

@ -0,0 +1,102 @@
package parser
import (
"bytes"
"io"
"strings"
"asciigoat.org/core/lexer"
)
// TextParser is a generic text parser.
type TextParser struct {
*lexer.Reader
pos lexer.Position
}
// Init initializes the [TextParser] with a non-nil [io.Reader].
func (p *TextParser) Init(r io.Reader) {
switch {
case p == nil || r == nil:
panic("invalid call")
case p.Reader != nil:
panic("parser already initialized")
default:
p.Reader = lexer.NewReader(r)
p.pos.Reset()
}
}
// InitBytes initializes the [TextParser] with a byte array
func (p *TextParser) InitBytes(b []byte) {
p.Init(bytes.NewReader(b))
}
// InitString initializes the [TextParser] with a byte array
func (p *TextParser) InitString(s string) {
p.Init(strings.NewReader(s))
}
// Discard shadows [lexer.Reader]'s, and takes in consideration
// new lines on the discarded data when moving the position
func (*TextParser) Discard() {
// TODO: consider new lines
panic("not implemented")
}
// Emit returns the accepted text, its position, and
// moves the cursor position accordingly
func (p *TextParser) Emit() (lexer.Position, string) {
pos := p.pos
s := p.Reader.Emit()
// TODO: consider new lines
p.pos.StepN(len(s))
return pos, s
}
// Step discards what's been accepted and increments the
// position assuming they all increment the column counter
func (p *TextParser) Step() {
s := p.Reader.Emit()
p.pos.StepN(len(s))
}
// StepLine discards what's been accepted and moves then
// position to the beginning of the next line
func (p *TextParser) StepLine() {
p.Reader.Discard()
p.pos.StepLine()
}
// Position returns the position of the first character
// of the accepted text
func (p *TextParser) Position() lexer.Position {
return p.pos
}
// AcceptNewLine checks if next is a new line.
// It accepts "\n", "\n\r", "\r" and "\r\n".
func (p *TextParser) AcceptNewLine() bool {
r1, _, err := p.ReadRune()
switch {
case err != nil:
return false
case r1 == '\n':
p.AcceptRune('\r')
return true
case r1 == '\r':
p.AcceptRune('\n')
return true
default:
p.UnreadRune()
return false
}
}
// AcceptRune checks if next is the specified rune
func (p *TextParser) AcceptRune(r rune) bool {
return p.Accept(func(r2 rune) bool {
return r == r2
})
}
Loading…
Cancel
Save